4 Commits
Author SHA1 Message Date
kartiandClaude Opus 5 7abbd24d34 docs: sentence-case the redacted node name
arena-environments / validate (3.11) (push) Successful in 1m9s
arena-environments / validate (3.12) (push) Successful in 1m21s
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012AaUFYkUTsJn1fnJ89qbvW
2026-09-15 12:16:04 -07:00
kartiandClaude Opus 5 ef01bde068 docs: redact the reference node's address and hostname
arena-environments / validate (3.11) (push) Successful in 1m23s
arena-environments / validate (3.12) (push) Successful in 1m8s
The eval docs named spark-1 by fleet hostname and published its inference
endpoint (a tailnet address and port) plus the fact that it answers without
an API key. This repo is PUBLIC, so that was a standing disclosure of an
internal, unauthenticated service to anonymous readers.

Endpoints now come from $SPARK_BASE_URL, which the operator exports, and the
host is referred to as "the reference node" -- the convention the compute
repo's docs already use.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012AaUFYkUTsJn1fnJ89qbvW
2026-09-15 12:15:37 -07:00
karti 61939676a5 Pin Arena environments to stable Verifiers
arena-environments / validate (3.11) (push) Successful in 1m11s
arena-environments / validate (3.12) (push) Successful in 1m12s
2026-08-25 10:33:35 -07:00
kartiandClaude Opus 5 e4cc2bf1c3 docs: the scope, the plan, the post-review execution plan, and the eval runbook
MULTI_TURN.md scopes the multi-turn gap and records the finding that made it
cheap: multi-turn needs no container and no real harness. vf.Env.run programs the
control flow host-side and the simulator runs in-process as the user, with the
harness left null.

PLAN.md carries the settled decisions. EXECUTION.md is the post-adversarial-review
plan — every position in it survived a reviewer, and where a design spec was
overturned the corrected position is what is written down.

Two corrections are marked in place rather than silently rewritten, because both
were believed and acted on:

- The provenance hole is src/arena/index.ts, not offices/sites.ts. Mutating
  offices/sites.ts produces a bit-identical episode; index.ts re-exports the
  scripted baselines that ARE the reward denominator, and a halved office-nav
  baseline moves return 4.744 -> 4.098 while every tera hash gate prints ok.
- office-jobs-v1 is not phantom. It was absent at 13:00 and present at 15:50,
  because another session fast-forward-merged it into the shared tera tree
  mid-session. The counts are twelve, five and twenty.

docs/FIRST_EVAL.md is the runbook for the first evaluation Arena ever completed:
seven environments, 224 episodes, 223 scored, against brain-qwen38-dspark. It
warns that the mean is sum(score x weight) — an unweighted mean over components
is a different number, and it is how six of seven means were first misreported.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-21 15:55:43 -07:00